def run(self):
name = self.config.get('Configuration', 'channel') if self.config.has_option('Configuration', 'channel') else '_'
timestamp = datetime.datetime.now().strftime("%y%m%d")
tmpName = self.tmpDir + '/skim_' + name + '_' + region + '_' + timestamp + '_tmp.root'
destName = self.pathOUT + '/skim_' + name + '_' + region + '_' + timestamp + '.root'
sampleTree = SampleTree(self.fileNames, config=self.config)
if self.config.has_option('Plot_general', 'controlSample'):
controlSampleDict = eval(self.config.get('Plot_general', 'controlSample'))
controlSample = controlSampleDict[self.region] if self.region in controlSampleDict else -1
sampleTree.addOutputBranch("controlSample", lambda x: controlSample, branchType="i")
print("INFO: setting controlSample to", controlSample)
sampleTree.addOutputTree(tmpName, cut='1', branches='*', friend=False)
sampleTree.process()
# copy to final destination
if sampleTree.getNumberOfOutputTrees() > 0:
try:
self.fileLocator.cp(tmpName, destName, force=True)
print('copy ', tmpName, destName)
if not self.fileLocator.isValidRootFile(destName):
print("\x1b[31mERROR: copy failed, output is broken!\x1b[0m")
else:
try:
self.fileLocator.rm(tmpName)
except Exception as e:
print(e)
except Exception as e:
print("\x1b[31mERROR: copy failed!", e, "\x1b[0m")
def run(self):
inputFileNames = [
"{path}/{sample}/{fileName}".format(
path=self.config.get('Directories', 'HADDin'),
sample=self.sampleIdentifier,
fileName=self.fileLocator.getFilenameAfterPrep(fileName))
for fileName in self.fileNames
]
outputFileName = self.getTemporaryFileName()
self.fileLocator.makedirs('/'.join(outputFileName.split('/')[:-1]))
command = self.commandTemplate.format(output=outputFileName,
inputs=' '.join(inputFileNames),
f="-f" if self.force else "")
if self.debug:
print("DEBUG: run \x1b[34m", command, "\x1b[0m")
if self.useChain:
# use sampleTree class (can e.g. drop branches at the same time)
sampleTree = SampleTree(inputFileNames, config=self.config)
try:
removeBranches = eval(
self.config.get('General', 'remove_branches'))
for removeBranch in removeBranches:
sampleTree.addBranchToBlacklist(removeBranch)
print("DEBUG: disable branch ", removeBranch)
except Exception as e:
print("DEBUG: could not disable branch:", e)
sampleTree.addOutputTree(outputFileName, cut='1', branches='*')
sampleTree.process()
result = 0
else:
# standard hadd
result = self.fileLocator.runCommand(command)
print("INFO: hadd returned ", result)
if result == 0:
finalOutputFileName = self.getOutputFileName()
print("move file to final destination: \x1b[34m",
finalOutputFileName, "\x1b[0m")
self.fileLocator.makedirs('/'.join(
finalOutputFileName.split('/')[:-1]))
resultCopy = self.fileLocator.cp(outputFileName,
finalOutputFileName, self.force)
if not resultCopy:
print("\x1b[31mERROR: copy failed\n from:", outputFileName,
"\n to:", finalOutputFileName, "\n force:", self.force,
"\x1b[0m")
raise Exception("FileCopyError")
# try to delete temporary file
try:
self.fileLocator.rm(outputFileName)
except Exception as e:
print("ERROR: could not delete temporary file:",
outputFileName, " => ", e)
print("INFO: done.")
else:
raise Exception("HaddError")
def run(self):
inputFileNames = ["{path}/{sample}/{fileName}".format(path=self.config.get('Directories','HADDin'), sample=self.sampleIdentifier, fileName=self.fileLocator.getFilenameAfterPrep(fileName)) for fileName in self.fileNames]
outputFileName = self.getTemporaryFileName()
self.fileLocator.makedirs('/'.join(outputFileName.split('/')[:-1]))
command = self.commandTemplate.format(output=outputFileName, inputs=' '.join(inputFileNames), f="-f" if self.force else "")
if self.debug:
print ("DEBUG: run \x1b[34m", command, "\x1b[0m")
if self.useChain:
# use sampleTree class (can e.g. drop branches at the same time)
sampleTree = SampleTree(inputFileNames, config=self.config)
try:
removeBranches = eval(self.config.get('General', 'remove_branches'))
for removeBranch in removeBranches:
sampleTree.addBranchToBlacklist(removeBranch)
print("DEBUG: disable branch ", removeBranch)
except Exception as e:
print("DEBUG: could not disable branch:", e)
sampleTree.addOutputTree(outputFileName, cut='1', branches='*')
sampleTree.process()
result = 0
else:
# standard hadd
result = self.fileLocator.runCommand(command)
print ("INFO: hadd returned ", result)
if result == 0:
finalOutputFileName = self.getOutputFileName()
print("move file to final destination: \x1b[34m", finalOutputFileName, "\x1b[0m")
self.fileLocator.makedirs('/'.join(finalOutputFileName.split('/')[:-1]))
resultCopy = self.fileLocator.cp(outputFileName, finalOutputFileName, self.force)
if not resultCopy:
print("\x1b[31mERROR: copy failed\n from:", outputFileName, "\n to:", finalOutputFileName, "\n force:", self.force, "\x1b[0m")
raise Exception("FileCopyError")
# try to delete temporary file
try:
self.fileLocator.rm(outputFileName)
except Exception as e:
print("ERROR: could not delete temporary file:", outputFileName, " => ", e)
print("INFO: done.")
else:
raise Exception("HaddError")
def run(self):
name = self.config.get('Configuration',
'channel') if self.config.has_option(
'Configuration', 'channel') else '_'
timestamp = datetime.datetime.now().strftime("%y%m%d")
tmpName = self.tmpDir + '/skim_' + name + '_' + region + '_' + timestamp + '_tmp.root'
destName = self.pathOUT + '/skim_' + name + '_' + region + '_' + timestamp + '.root'
sampleTree = SampleTree(self.fileNames, config=self.config)
if self.config.has_option('Plot_general', 'controlSample'):
controlSampleDict = eval(
self.config.get('Plot_general', 'controlSample'))
controlSample = controlSampleDict[
self.region] if self.region in controlSampleDict else -1
sampleTree.addOutputBranch("controlSample",
lambda x: controlSample,
branchType="i")
print("INFO: setting controlSample to", controlSample)
sampleTree.addOutputTree(tmpName, cut='1', branches='*', friend=False)
sampleTree.process()
# copy to final destination
if sampleTree.getNumberOfOutputTrees() > 0:
try:
self.fileLocator.cp(tmpName, destName, force=True)
print('copy ', tmpName, destName)
if not self.fileLocator.isValidRootFile(destName):
print(
"\x1b[31mERROR: copy failed, output is broken!\x1b[0m")
else:
try:
self.fileLocator.rm(tmpName)
except Exception as e:
print(e)
except Exception as e:
print("\x1b[31mERROR: copy failed!", e, "\x1b[0m")
def run(self):
nFilesProcessed = 0
nFilesFailed = 0
for subJob in self.subJobs:
# only process if output is non-existing/broken or --force was used
if self.opts.force or not self.fileLocator.isValidRootFile(subJob['outputFileName']):
# create directories
outputFolder = '/'.join(subJob['outputFileName'].split('/')[:-1])
tmpFolder = '/'.join(subJob['tmpFileName'].split('/')[:-1])
self.fileLocator.makedirs(outputFolder)
self.fileLocator.makedirs(tmpFolder)
# load sample tree
sampleTree = SampleTree(subJob['localInputFileNames'], config=self.config)
if not sampleTree.tree:
print "trying fallback...", len(subJob['inputFileNames'])
if len(subJob['inputFileNames']) == 1:
# try original naming scheme if reading directly from Heppy/Nano ntuples (without prep)
fileNameOriginal = self.pathIN + '/' + subJob['inputFileNames'][0]
print "FO:", fileNameOriginal
xrootdRedirector = self.fileLocator.getRedirector(fileNameOriginal)
sampleTree = SampleTree([fileNameOriginal], config=self.config, xrootdRedirector=xrootdRedirector)
if not sampleTree.tree:
print "\x1b[31mERROR: file does not exist or is broken, will be SKIPPED!\x1b[0m"
nFilesFailed += 1
continue
else:
print "\x1b[31mERROR: file does not exist or is broken, will be SKIPPED! (old naming scheme not supported for joining multipel files)\x1b[0m"
nFilesFailed += 1
continue
# to use this syntax, use "--addCollections Sys.Vtype" for a config file entry like this:
# [Sys]
# Vtype = VtypeCorrector.VtypeCorrector(channel='Zll')
# (instead of passing the tree in the constructor, the setTree method can be used)
pyModules = []
versionTable = []
for collection in self.collections:
if '.' in collection:
section = collection.split('.')[0]
key = collection.split('.')[1]
if self.config.has_section(section) and self.config.has_option(section, key):
pyCode = self.config.get(section, key)
elif '(' in collection and collection.endswith(')'):
print "WARNING: config option", collection, " not found, interpreting it as Python code!"
pyCode = collection
else:
print "\x1b[31mERROR: config option not found:", collection, ". To specify Python code directly, pass a complete constructor, e.g. --addCollections 'Module.Class()'. Module has to be placed in python/myutils/ folder.\x1b[0m"
raise Exception("ConfigError")
# import module from myutils
moduleName = pyCode.split('(')[0].split('.')[0].strip()
if self.debug:
print "DEBUG: import module:", moduleName
print("\x1b[33mDEBUG: " + collection + ": run PYTHON code:\n"+pyCode+"\x1b[0m")
globals()[moduleName] = importlib.import_module(".{module}".format(module=moduleName), package="myutils")
# get object
wObject = eval(pyCode)
# pass the tree and other variables if needed to finalize initialization
if hasattr(wObject, "customInit") and callable(getattr(wObject, "customInit")):
wObject.customInit({'config': self.config,
'sampleTree': sampleTree,
'tree': sampleTree.tree,
'sample': self.sample,
'channel': self.channel,
'pathIN': self.pathIN,
'pathOUT': self.pathOUT,
})
# add callbacks if the objects provides any
if hasattr(wObject, "processEvent") and callable(getattr(wObject, "processEvent")):
sampleTree.addCallback('event', wObject.processEvent)
for cb in ["finish", "prepareOutput"]:
if hasattr(wObject, cb) and callable(getattr(wObject, cb)):
sampleTree.addCallback(cb, getattr(wObject, cb))
# add branches
if hasattr(wObject, "getBranches") and callable(getattr(wObject, "getBranches")):
sampleTree.addOutputBranches(wObject.getBranches())
pyModules.append(wObject)
versionTable.append([moduleName, wObject.getVersion() if hasattr(wObject, "getVersion") else 0])
else:
print "\x1b[31mERROR: config option not found:", collection, " the format should be: [Section].[Option]\x1b[0m"
raise Exception("ConfigError")
for moduleName, moduleVersion in versionTable:
print " > {m}:{v}".format(m=moduleName, v=moduleVersion)
# DEPRECATED, do not use anymore ---> use BranchTools.TreeFormulas()
if 'addbranches' in self.collections:
writeNewVariables = eval(self.config.get("Regression", "writeNewVariablesDict"))
sampleTree.addOutputBranches(writeNewVariables)
# DEPRECATED, do not use anymore ---> use BranchTools.Drop()
if 'removebranches' in self.collections:
bl_branch = eval(config.get('Branches', 'useless_branch'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
bl_branch = eval(config.get('Branches', 'useless_after_sys'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
# define output file
sampleTree.addOutputTree(subJob['tmpFileName'], cut='1', branches='*', friend=self.opts.friend)
# run processing
for pyModule in pyModules:
if hasattr(pyModule, "beforeProcessing"):
getattr(pyModule, "beforeProcessing")()
sampleTree.process()
for pyModule in pyModules:
if hasattr(pyModule, "afterProcessing"):
getattr(pyModule, "afterProcessing")()
# if output trees have been produced: copy temporary file to output folder
if sampleTree.getNumberOfOutputTrees() > 0:
try:
self.fileLocator.cp(subJob['tmpFileName'], subJob['outputFileName'], force=True)
print 'copy ', subJob['tmpFileName'], subJob['outputFileName']
if self.verifyCopy:
if not self.fileLocator.isValidRootFile(subJob['outputFileName']):
print 'INFO: output at final destination broken, try to copy again from scratch disk to final destination...'
self.fileLocator.cp(subJob['tmpFileName'], subJob['outputFileName'], force=True)
print 'INFO: second attempt copy done!'
if not self.fileLocator.isValidRootFile(subJob['outputFileName']):
print '\x1b[31mERROR: output still broken!\x1b[0m'
nFilesFailed += 1
raise Exception("FileCopyError")
else:
print 'INFO: file is good after second attempt!'
except Exception as e:
print e
print "\x1b[31mERROR: copy from scratch to final destination failed!!\x1b[0m"
# delete temporary file
try:
self.fileLocator.rm(subJob['tmpFileName'])
except Exception as e:
print e
print "WARNING: could not delete file on scratch!"
# clean up
if hasattr(wObject, "cleanUp") and callable(getattr(wObject, "cleanUp")):
getattr(wObject, "cleanUp")()
else:
print 'SKIP:', subJob['inputFileNames']
if nFilesFailed > 0:
raise Exception("ProcessingIncomplete")
class CacheTraining(object):
def __init__(self, config, sampleIdentifier, trainingRegions, splitFilesChunks=1, chunkNumber=1, splitFilesChunkSize=-1, force=False):
self.config = config
self.force = force
self.sampleIdentifier = sampleIdentifier
self.trainingRegions = trainingRegions
self.sampleTree = None
self.samplesPath = self.config.get('Directories', 'MVAin')
self.samplesDefinitions = self.config.get('Directories','samplesinfo')
self.samplesInfo = ParseInfo(self.samplesDefinitions, self.samplesPath)
self.sampleFilesFolder = self.config.get('Directories', 'samplefiles')
self.backgroundSampleNames = list(set(sum([eval(self.config.get(trainingRegion, 'backgrounds')) for trainingRegion in self.trainingRegions], [])))
self.signalSampleNames = list(set(sum([eval(self.config.get(trainingRegion, 'signals')) for trainingRegion in self.trainingRegions], [])))
self.samples = self.samplesInfo.get_samples(list(set(self.backgroundSampleNames + self.signalSampleNames)))
self.trainingRegionsDict = {}
for trainingRegion in self.trainingRegions:
treeCutName = config.get(trainingRegion, 'treeCut')
treeVarSet = config.get(trainingRegion, 'treeVarSet').strip()
#systematics = [x for x in config.get('systematics', 'systematics').split(' ') if len(x.strip())>0]
systematics = eval(config.get(trainingRegion, 'systematics')) if config.has_option(trainingRegion, 'systematics') else []
mvaVars = config.get(treeVarSet, 'Nominal').split(' ')
weightVars = []
#for systematic in systematics:
for syst in systematics:
systNameUp = syst+'_UP' if self.config.has_option('Weights',syst+'_UP') else syst+'_Up'
systNameDown = syst+'_DOWN' if self.config.has_option('Weights',syst+'_DOWN') else syst+'_Down'
weightVars += [self.config.get('Weights',systNameUp), self.config.get('Weights',systNameDown)]
self.trainingRegionsDict[trainingRegion] = {
'cut': config.get('Cuts', treeCutName),
'vars': mvaVars,
'weightVars': weightVars,
}
self.TrainCut = config.get('Cuts', 'TrainCut')
self.EvalCut = config.get('Cuts', 'EvalCut')
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.splitFilesChunkSize = splitFilesChunkSize
VHbbNameSpace=config.get('VHbbNameSpace','library')
ROOT.gSystem.Load(VHbbNameSpace)
def printInfo(self):
print ("REGION:".ljust(24),"CUT:")
for trainingRegion,trainingRegionInfo in self.trainingRegionsDict.iteritems():
print (" > ",trainingRegion.ljust(20), trainingRegionInfo['cut'])
def run(self):
# ----------------------------------------------------------------------------------------------------------------------
# cache samples
# ----------------------------------------------------------------------------------------------------------------------
for sampleToCache in [self.sampleIdentifier]:
print ('*'*80)
print (' ',sampleToCache)
print ('*'*80)
# prepare caches for training and evaluation samples
treeCaches = []
self.sampleTree = None
# use all (sub)samples which come from the same files (sampleIdentifier)
subsamples = [x for x in self.samples if x.identifier == sampleToCache]
# list of branches to keep for use as MVA input variables
branchListOfMVAVars = BranchList()
for sample in subsamples:
for trainingRegion,trainingRegionInfo in self.trainingRegionsDict.iteritems():
for additionalCut in [self.TrainCut, self.EvalCut]:
branchListOfMVAVars.addCut(trainingRegionInfo['vars'])
for weightVar in trainingRegionInfo['weightVars']:
branchListOfMVAVars.addCut(weightVar)
branchListOfMVAVars.addCut(self.config.get('Weights', 'weightF'))
mvaBranches = branchListOfMVAVars.getListOfBranches()
# loop over all samples
for sample in subsamples:
# add cuts for all training regions
for trainingRegion,trainingRegionInfo in self.trainingRegionsDict.iteritems():
# add cuts for training and evaluation
for additionalCut in [self.TrainCut, self.EvalCut]:
# cuts
sampleCuts = [sample.subcut]
if additionalCut:
sampleCuts.append(additionalCut)
if trainingRegionInfo['cut']:
sampleCuts.append(trainingRegionInfo['cut'])
# add cache object
tc = TreeCache.TreeCache(
name='{region}_{sample}_{tr}'.format(region=trainingRegion, sample=sample.name, tr='TRAIN' if additionalCut==self.TrainCut else 'EVAL'),
sample=sample.name,
cutList=sampleCuts,
inputFolder=self.samplesPath,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
branches=mvaBranches,
config=self.config,
debug=True
)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
if not isCached or self.force:
if isCached:
tc.deleteCachedFiles(chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree({'name': sample.identifier, 'folder': self.samplesPath}, splitFilesChunkSize=self.splitFilesChunkSize, chunkNumber=self.chunkNumber, config=self.config, saveMemory=True)
treeCaches.append(tc.setSampleTree(self.sampleTree).cache())
if len(treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print ("nothing to do!")
# TODO: this can also be made a separate module
if 'addbranches' in collections:
writeNewVariables = eval(config.get("Regression", "writeNewVariablesDict"))
sampleTree.addOutputBranches(writeNewVariables)
if 'removebranches' in collections:
bl_branch = eval(config.get('Branches', 'useless_branch'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
bl_branch = eval(config.get('Branches', 'useless_after_sys'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
# define output file
sampleTree.addOutputTree(tmpFileName, cut='1', branches='*')
sampleTree.process()
# copy temporary file to output folder
if opts.force and fileLocator.exists(outputFileName):
fileLocator.rm(outputFileName)
try:
fileLocator.cp(tmpFileName, outputFileName)
except Exception as e:
print "\x1b[31mERROR: copy from scratch to final destination failed!!\x1b[0m"
print e
try:
fileLocator.rm(tmpFileName)
except Exception as e:
print "ERROR: could not delete file on scratch!"
# TODO: this can also be made a separate module
if 'addbranches' in collections:
writeNewVariables = eval(config.get("Regression", "writeNewVariablesDict"))
sampleTree.addOutputBranches(writeNewVariables)
if 'removebranches' in collections:
bl_branch = eval(config.get('Branches', 'useless_branch'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
bl_branch = eval(config.get('Branches', 'useless_after_sys'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
# define output file
sampleTree.addOutputTree(tmpFileName, cut='1', branches='*')
sampleTree.process()
# copy temporary file to output folder
if opts.force and fileLocator.exists(outputFileName):
fileLocator.rm(outputFileName)
try:
fileLocator.cp(tmpFileName, outputFileName)
except Exception as e:
print "\x1b[31mERROR: copy from scratch to final destination failed!!\x1b[0m"
print e
try:
fileLocator.rm(tmpFileName)
except Exception as e:
print "ERROR: could not delete file on scratch!"
class CachePlot(object):
def __init__(self,
config,
sampleIdentifier,
regions,
splitFilesChunks=1,
chunkNumber=1,
splitFilesChunkSize=-1,
forceRedo=False,
fileList=None):
self.config = config
self.sampleIdentifier = sampleIdentifier
self.regions = list(set(regions))
self.forceRedo = forceRedo
self.sampleTree = None
self.samplesPath = self.config.get('Directories', 'plottingSamples')
self.samplesInfo = ParseInfo(samples_path=self.samplesPath,
config=self.config)
self.sampleFilesFolder = self.config.get('Directories', 'samplefiles')
self.sampleNames = list(
eval(self.config.get('Plot_general', 'samples')))
self.dataNames = list(eval(self.config.get('Plot_general', 'Data')))
self.samples = self.samplesInfo.get_samples(self.sampleNames +
self.dataNames)
self.regionsDict = {}
for region in self.regions:
treeCut = config.get('Cuts', region)
self.regionsDict[region] = {'cut': treeCut}
self.splitFilesChunkSize = splitFilesChunkSize
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.fileList = FileList.decompress(fileList) if fileList else None
VHbbNameSpace = config.get('VHbbNameSpace', 'library')
returnCode = ROOT.gSystem.Load(VHbbNameSpace)
if returnCode != 0:
print(
"\x1b[31mERROR: loading VHbbNameSpace failed with code %d\x1b[0m"
% returnCode)
else:
print("INFO: loaded VHbbNameSpace: %s" % VHbbNameSpace)
def printInfo(self):
print("REGION:".ljust(24), "CUT:")
for region, regionInfo in self.regionsDict.iteritems():
print(" > ", region.ljust(20), regionInfo['cut'])
def run(self):
# keep additional branches for plotting
try:
keepBranchesPlot = eval(
self.config.get('Branches', 'keep_branches_plot'))
except:
keepBranchesPlot = []
try:
keepBranchesPlot += eval(
self.config.get('Branches', 'keep_branches'))
except:
pass
# also keep some branches which might be used later in variables definition and weights
try:
for section in self.config.sections():
try:
if section.startswith(
'plotDef:') and self.config.has_option(
section, 'relPath'):
keepBranchesPlot.append(
self.config.get(section, 'relPath'))
except Exception as e:
print("\x1b[31mWARNING: config error in:", section, "=>",
e, "\x1b[0m")
except Exception as e2:
print(
"\x1b[31mERROR: config file contains an error! automatic selection of branches to keep will not work!\x1b[0m"
)
print(e2)
try:
keepBranchesPlot.append(self.config.get('Weights', 'weightF'))
except:
pass
# plotting region cut
for region, regionInfo in self.regionsDict.iteritems():
keepBranchesPlot.append(regionInfo['cut'])
keepBranchesPlotFinal = BranchList(
keepBranchesPlot).getListOfBranches()
print("KEEP:", keepBranchesPlotFinal)
# ----------------------------------------------------------------------------------------------------------------------
# cache samples
# ----------------------------------------------------------------------------------------------------------------------
for sampleToCache in [self.sampleIdentifier]:
print('*' * 80)
print(' ', sampleToCache)
print('*' * 80)
# prepare caches for training and evaluation samples
treeCaches = []
sampleTree = None
# for all (sub)samples which come from the same files (sampleIdentifier)
subsamples = [
x for x in self.samples if x.identifier == sampleToCache
]
for sample in subsamples:
# add cuts for all training regions
for region, regionInfo in self.regionsDict.iteritems():
configSection = 'Plot:%s' % region
# cuts
sampleCuts = [sample.subcut]
if regionInfo['cut']:
sampleCuts.append(regionInfo['cut'])
if self.config.has_option(configSection, 'Datacut'):
sampleCuts.append(
self.config.get(configSection, 'Datacut'))
if self.config.has_option('Plot_general',
'addBlindingCut'):
sampleCuts.append(
self.config.has_option('Plot_general',
'addBlindingCut'))
# arbitrary (optional) name for the output tree, used for print-out (the TreeCache object has no idea what it is doing, e.g. dc, plot etc.)
cacheName = 'plot:{region}_{sample}'.format(
region=region, sample=sample.name)
# add cache object
tc = TreeCache.TreeCache(
name=cacheName,
sample=sample.name,
cutList=sampleCuts,
inputFolder=self.samplesPath,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
fileList=self.fileList,
branches=keepBranchesPlotFinal,
config=self.config,
debug=True)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
if not isCached or self.forceRedo:
if isCached:
tc.deleteCachedFiles(chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree(
{
'name': sample.identifier,
'folder': self.samplesPath
},
splitFilesChunkSize=self.splitFilesChunkSize,
chunkNumber=self.chunkNumber,
config=self.config,
saveMemory=True)
if not self.sampleTree or not self.sampleTree.tree:
print(
"\x1b[31mERROR: creation of sample tree failed!!\x1b[0m"
)
raise Exception("CreationOfSampleTreeFailed")
# consistency check on the file list at submission time and now
fileListNow = self.sampleTree.getSampleFileNameChunk(
self.chunkNumber)
if self.fileList and (sorted(self.fileList) !=
sorted(fileListNow)):
print(
"\x1b[31mERROR: sample files have changed between submission and run of the job!\x1b[0m"
)
raise Exception("SampleFilesHaveChanged")
treeCaches.append(
tc.setSampleTree(self.sampleTree).cache())
else:
print("INFO: already cached!", tc, "(", tc.hash, ")")
if len(treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print("nothing to do!")
class CacheDatacards(object):
def __init__(self,
config,
regions,
sampleToCache,
splitFilesChunks=1,
chunkNumber=1,
splitFilesChunkSize=-1,
forceRedo=False,
fileList=None,
verbose=False):
self.verbose = verbose or ('XBBDEBUG' in os.environ)
self.config = config
self.regions = regions
self.treeCaches = []
self.sampleTree = None
self.sampleToCache = sampleToCache
self.forceRedo = forceRedo
# settings which part of input files to process
self.splitFilesChunkSize = splitFilesChunkSize
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.fileList = FileList.decompress(fileList) if fileList else None
# initialize Datacard objects
self.dcMakers = [
Datacard(config=self.config, region=region)
for region in self.regions
]
# make a minimum list of samples which is needed to produce all the Datacard regions at the same time
def getAllSamples(self):
samples = []
for dcMaker in self.dcMakers:
for sample in dcMaker.getAllSamples():
if len([x for x in samples if x.name == sample.name]) < 1:
samples.append(sample)
return samples
def prepare(self):
if len(self.dcMakers) > 0:
self.treeCaches = []
self.sampleTree = None
# cuts
allSamples = self.getAllSamples()
subsamples = [
x for x in allSamples if x.identifier == self.sampleToCache
]
# loop over all datacard regions
for dcMaker in self.dcMakers:
# loop over all subsamples (which come from the same root tree files)
for sample in subsamples:
# combine subcut and systematics cut with logical AND
# systematics cuts are combined with logical OR, such that 1 cache file can be used for all the systematics
isData = (sample.type == 'DATA')
systematicsCuts = sorted(
list(
set([
x['cachecut']
for x in dcMaker.getSystematicsList(
isData=isData)
])))
sampleCuts = {
'AND': [sample.subcut, {
'OR': systematicsCuts
}]
}
if self.verbose:
print(
json.dumps(sampleCuts,
sort_keys=True,
indent=8,
default=str))
# make list of branches to keep in root file
branchList = BranchList(sample.subcut)
branchList.addCut(
[x['cachecut'] for x in dcMaker.getSystematicsList()])
branchList.addCut(
[x['cut'] for x in dcMaker.getSystematicsList()])
branchList.addCut(
[x['var'] for x in dcMaker.getSystematicsList()])
branchList.addCut(
[x['weight'] for x in dcMaker.getSystematicsList()])
branchList.addCut(self.config.get('Weights', 'weightF'))
branchList.addCut(
eval(self.config.get('Branches', 'keep_branches')))
branchesToKeep = branchList.getListOfBranches()
# arbitrary (optional) name for the output tree, used for print-out (the TreeCache object has no idea what it is doing, e.g. dc, plot etc.)
cacheName = 'dc:{region}_{sample}'.format(
region=dcMaker.getRegion(), sample=sample.name)
# add cache object
tc = TreeCache.TreeCache(
name=cacheName,
sample=sample.name,
cutList=sampleCuts,
cutSequenceMode='TREE',
branches=branchesToKeep,
inputFolder=dcMaker.path,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
fileList=self.fileList,
config=self.config,
debug=self.verbose)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
print(
"check if sample \x1b[34m{sample}\x1b[0m part {part} is cached:"
.format(sample=sample.name,
part=self.chunkNumber), isCached)
if not isCached or self.forceRedo:
if isCached:
tc.deleteCachedFiles(chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree(
{
'name': sample.identifier,
'folder': dcMaker.path
},
splitFilesChunkSize=self.splitFilesChunkSize,
chunkNumber=self.chunkNumber,
config=self.config,
saveMemory=True)
if not self.sampleTree or not self.sampleTree.tree:
print(
"\x1b[31mERROR: creation of sample tree failed!!\x1b[0m"
)
raise Exception("CreationOfSampleTreeFailed")
# consistency check on the file list at submission time and now
fileListNow = self.sampleTree.getSampleFileNameChunk(
self.chunkNumber)
if self.fileList and (sorted(self.fileList) !=
sorted(fileListNow)):
print(
"\x1b[31mERROR: sample files have changed between submission and run of the job!\x1b[0m"
)
raise Exception("SampleFilesHaveChanged")
# connect the TreeCache object to the input sampleTree and add it to the list of cached trees
self.treeCaches.append(
tc.setSampleTree(self.sampleTree).cache())
else:
print("WARNING: no datacard regions added, nothing to do.")
return self
def run(self):
if len(self.treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print("nothing to do!")
class CacheTraining(object):
def __init__(self,
config,
sampleIdentifier,
trainingRegions,
splitFilesChunks=1,
chunkNumber=1,
splitFilesChunkSize=-1,
force=False):
self.config = config
self.force = force
self.sampleIdentifier = sampleIdentifier
self.trainingRegions = trainingRegions
self.sampleTree = None
self.samplesPath = self.config.get('Directories', 'MVAin')
self.samplesDefinitions = self.config.get('Directories', 'samplesinfo')
self.samplesInfo = ParseInfo(self.samplesDefinitions, self.samplesPath)
self.sampleFilesFolder = self.config.get('Directories', 'samplefiles')
self.backgroundSampleNames = list(
set(
sum([
eval(self.config.get(trainingRegion, 'backgrounds'))
for trainingRegion in self.trainingRegions
], [])))
self.signalSampleNames = list(
set(
sum([
eval(self.config.get(trainingRegion, 'signals'))
for trainingRegion in self.trainingRegions
], [])))
self.samples = self.samplesInfo.get_samples(
list(set(self.backgroundSampleNames + self.signalSampleNames)))
self.trainingRegionsDict = {}
for trainingRegion in self.trainingRegions:
treeCutName = config.get(trainingRegion, 'treeCut')
treeVarSet = config.get(trainingRegion, 'treeVarSet').strip()
systematics = [
x for x in config.get('systematics', 'systematics').split(' ')
if len(x.strip()) > 0
]
mvaVars = []
for systematic in systematics:
mvaVars += config.get(treeVarSet,
systematic).strip().split(' ')
self.trainingRegionsDict[trainingRegion] = {
'cut': config.get('Cuts', treeCutName),
'vars': mvaVars,
}
self.TrainCut = config.get('Cuts', 'TrainCut')
self.EvalCut = config.get('Cuts', 'EvalCut')
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.splitFilesChunkSize = splitFilesChunkSize
VHbbNameSpace = config.get('VHbbNameSpace', 'library')
ROOT.gSystem.Load(VHbbNameSpace)
def printInfo(self):
print("REGION:".ljust(24), "CUT:")
for trainingRegion, trainingRegionInfo in self.trainingRegionsDict.iteritems(
):
print(" > ", trainingRegion.ljust(20), trainingRegionInfo['cut'])
def run(self):
# ----------------------------------------------------------------------------------------------------------------------
# cache samples
# ----------------------------------------------------------------------------------------------------------------------
for sampleToCache in [self.sampleIdentifier]:
print('*' * 80)
print(' ', sampleToCache)
print('*' * 80)
# prepare caches for training and evaluation samples
treeCaches = []
self.sampleTree = None
# use all (sub)samples which come from the same files (sampleIdentifier)
subsamples = [
x for x in self.samples if x.identifier == sampleToCache
]
# list of branches to keep for use as MVA input variables
branchListOfMVAVars = BranchList()
for sample in subsamples:
for trainingRegion, trainingRegionInfo in self.trainingRegionsDict.iteritems(
):
for additionalCut in [self.TrainCut, self.EvalCut]:
branchListOfMVAVars.addCut(trainingRegionInfo['vars'])
branchListOfMVAVars.addCut(self.config.get('Weights', 'weightF'))
mvaBranches = branchListOfMVAVars.getListOfBranches()
# loop over all samples
for sample in subsamples:
# add cuts for all training regions
for trainingRegion, trainingRegionInfo in self.trainingRegionsDict.iteritems(
):
# add cuts for training and evaluation
for additionalCut in [self.TrainCut, self.EvalCut]:
# cuts
sampleCuts = [sample.subcut]
if additionalCut:
sampleCuts.append(additionalCut)
if trainingRegionInfo['cut']:
sampleCuts.append(trainingRegionInfo['cut'])
# add cache object
tc = TreeCache.TreeCache(
name='{region}_{sample}_{tr}'.format(
region=trainingRegion,
sample=sample.name,
tr='TRAIN'
if additionalCut == self.TrainCut else 'EVAL'),
sample=sample.name,
cutList=sampleCuts,
inputFolder=self.samplesPath,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
branches=mvaBranches,
config=self.config,
debug=True)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
if not isCached or self.force:
if isCached:
tc.deleteCachedFiles(
chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree(
{
'name': sample.identifier,
'folder': self.samplesPath
},
splitFilesChunkSize=self.
splitFilesChunkSize,
chunkNumber=self.chunkNumber,
config=self.config,
saveMemory=True)
treeCaches.append(
tc.setSampleTree(self.sampleTree).cache())
if len(treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print("nothing to do!")
def run(self):
nFilesProcessed = 0
nFilesFailed = 0
for subJob in self.subJobs:
# only process if output is non-existing/broken or --force was used
if self.opts.force or not self.fileLocator.isValidRootFile(subJob['outputFileName']):
# create directories
outputFolder = '/'.join(subJob['outputFileName'].split('/')[:-1])
tmpFolder = '/'.join(subJob['tmpFileName'].split('/')[:-1])
self.fileLocator.makedirs(outputFolder)
self.fileLocator.makedirs(tmpFolder)
# load sample tree
sampleTree = SampleTree(subJob['localInputFileNames'], config=self.config)
if not sampleTree.tree:
print "trying fallback...", len(subJob['inputFileNames'])
if len(subJob['inputFileNames']) == 1:
# try original naming scheme if reading directly from Heppy/Nano ntuples (without prep)
fileNameOriginal = self.pathIN + '/' + subJob['inputFileNames'][0]
print "FO:", fileNameOriginal
xrootdRedirector = self.fileLocator.getRedirector(fileNameOriginal)
sampleTree = SampleTree([fileNameOriginal], config=self.config, xrootdRedirector=xrootdRedirector)
if not sampleTree.tree:
print "\x1b[31mERROR: file does not exist or is broken, will be SKIPPED!\x1b[0m"
nFilesFailed += 1
continue
else:
print "\x1b[31mERROR: file does not exist or is broken, will be SKIPPED! (old naming scheme not supported for joining multipel files)\x1b[0m"
nFilesFailed += 1
continue
# to use this syntax, use "--addCollections Sys.Vtype" for a config file entry like this:
# [Sys]
# Vtype = VtypeCorrector.VtypeCorrector(channel='Zll')
# (instead of passing the tree in the constructor, the setTree method can be used)
pyModules = []
for collection in self.collections:
if '.' in collection:
section = collection.split('.')[0]
key = collection.split('.')[1]
pyCode = self.config.get(section, key)
# import module from myutils
moduleName = pyCode.split('(')[0].split('.')[0].strip()
if self.debug:
print "DEBUG: import module:", moduleName
print("\x1b[33mDEBUG: " + collection + ": run PYTHON code:\n"+pyCode+"\x1b[0m")
globals()[moduleName] = importlib.import_module(".{module}".format(module=moduleName), package="myutils")
# get object
wObject = eval(pyCode)
# pass the tree and other variables if needed to finalize initialization
if hasattr(wObject, "customInit") and callable(getattr(wObject, "customInit")):
wObject.customInit({'config': self.config,
'sampleTree': sampleTree,
'tree': sampleTree.tree,
'sample': self.sample,
'channel': self.channel,
'pathIN': self.pathIN,
'pathOUT': self.pathOUT,
})
# add callbacks if the objects provides any
if hasattr(wObject, "processEvent") and callable(getattr(wObject, "processEvent")):
sampleTree.addCallback('event', wObject.processEvent)
# add branches
if hasattr(wObject, "getBranches") and callable(getattr(wObject, "getBranches")):
sampleTree.addOutputBranches(wObject.getBranches())
pyModules.append(wObject)
# DEPRECATED, do not use anymore ---> use BranchTools.TreeFormulas()
if 'addbranches' in self.collections:
writeNewVariables = eval(self.config.get("Regression", "writeNewVariablesDict"))
sampleTree.addOutputBranches(writeNewVariables)
# DEPRECATED, do not use anymore ---> use BranchTools.Drop()
if 'removebranches' in self.collections:
bl_branch = eval(config.get('Branches', 'useless_branch'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
bl_branch = eval(config.get('Branches', 'useless_after_sys'))
for br in bl_branch:
sampleTree.addBranchToBlacklist(br)
# define output file
sampleTree.addOutputTree(subJob['tmpFileName'], cut='1', branches='*', friend=self.opts.friend)
# run processing
for pyModule in pyModules:
if hasattr(pyModule, "beforeProcessing"):
getattr(pyModule, "beforeProcessing")()
sampleTree.process()
for pyModule in pyModules:
if hasattr(pyModule, "afterProcessing"):
getattr(pyModule, "afterProcessing")()
# if output trees have been produced: copy temporary file to output folder
if sampleTree.getNumberOfOutputTrees() > 0:
try:
self.fileLocator.cp(subJob['tmpFileName'], subJob['outputFileName'], force=True)
print 'copy ', subJob['tmpFileName'], subJob['outputFileName']
if self.verifyCopy:
if not self.fileLocator.isValidRootFile(subJob['outputFileName']):
print 'INFO: output at final destination broken, try to copy again from scratch disk to final destination...'
self.fileLocator.cp(subJob['tmpFileName'], subJob['outputFileName'], force=True)
print 'INFO: second attempt copy done!'
if not self.fileLocator.isValidRootFile(subJob['outputFileName']):
print '\x1b[31mERROR: output still broken!\x1b[0m'
nFilesFailed += 1
raise Exception("FileCopyError")
else:
print 'INFO: file is good after second attempt!'
except Exception as e:
print e
print "\x1b[31mERROR: copy from scratch to final destination failed!!\x1b[0m"
# delete temporary file
try:
self.fileLocator.rm(subJob['tmpFileName'])
except Exception as e:
print e
print "WARNING: could not delete file on scratch!"
# clean up
if hasattr(wObject, "cleanUp") and callable(getattr(wObject, "cleanUp")):
getattr(wObject, "cleanUp")()
else:
print 'SKIP:', subJob['inputFileNames']
if nFilesFailed > 0:
raise Exception("ProcessingIncomplete")
class CachePlot(object):
def __init__(self, config, sampleIdentifier, regions, splitFilesChunks=1, chunkNumber=1, splitFilesChunkSize=-1, forceRedo=False, fileList=None):
self.config = config
self.sampleIdentifier = sampleIdentifier
self.regions = list(set(regions))
self.forceRedo = forceRedo
self.sampleTree = None
self.samplesPath = self.config.get('Directories', 'plottingSamples')
self.samplesDefinitions = self.config.get('Directories','samplesinfo')
self.samplesInfo = ParseInfo(self.samplesDefinitions, self.samplesPath)
self.sampleFilesFolder = self.config.get('Directories', 'samplefiles')
self.sampleNames = eval(self.config.get('Plot_general', 'samples'))
self.dataNames = eval(self.config.get('Plot_general', 'Data'))
self.samples = self.samplesInfo.get_samples(self.sampleNames + self.dataNames)
self.regionsDict = {}
for region in self.regions:
treeCut = config.get('Cuts', region)
self.regionsDict[region] = {'cut': treeCut}
self.splitFilesChunkSize = splitFilesChunkSize
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.fileList = FileList.decompress(fileList) if fileList else None
VHbbNameSpace=config.get('VHbbNameSpace','library')
returnCode = ROOT.gSystem.Load(VHbbNameSpace)
if returnCode != 0:
print ("\x1b[31mERROR: loading VHbbNameSpace failed with code %d\x1b[0m"%returnCode)
else:
print ("INFO: loaded VHbbNameSpace: %s"%VHbbNameSpace)
def printInfo(self):
print ("REGION:".ljust(24),"CUT:")
for region,regionInfo in self.regionsDict.iteritems():
print (" > ",region.ljust(20), regionInfo['cut'])
def run(self):
# keep additional branches for plotting
try:
keepBranchesPlot = eval(self.config.get('Branches', 'keep_branches_plot'))
except:
keepBranchesPlot = []
try:
keepBranchesPlot += eval(self.config.get('Branches', 'keep_branches'))
except:
pass
# also keep some branches which might be used later in variables definition and weights
try:
for section in self.config.sections():
if section.startswith('plotDef:') and self.config.has_option(section, 'relPath'):
keepBranchesPlot.append(self.config.get(section, 'relPath'))
except Exception as e:
print("\x1b[31mERROR: config file contains an error! automatic selection of branches to keep will not work!\x1b[0m")
print(e)
try:
keepBranchesPlot.append(self.config.get('Weights', 'weightF'))
except:
pass
# plotting region cut
for region,regionInfo in self.regionsDict.iteritems():
keepBranchesPlot.append(regionInfo['cut'])
keepBranchesPlotFinal = BranchList(keepBranchesPlot).getListOfBranches()
print("KEEP:", keepBranchesPlotFinal)
# ----------------------------------------------------------------------------------------------------------------------
# cache samples
# ----------------------------------------------------------------------------------------------------------------------
for sampleToCache in [self.sampleIdentifier]:
print ('*'*80)
print (' ',sampleToCache)
print ('*'*80)
# prepare caches for training and evaluation samples
treeCaches = []
sampleTree = None
# for all (sub)samples which come from the same files (sampleIdentifier)
subsamples = [x for x in self.samples if x.identifier == sampleToCache]
for sample in subsamples:
# add cuts for all training regions
for region,regionInfo in self.regionsDict.iteritems():
configSection = 'Plot:%s'%region
# cuts
sampleCuts = [sample.subcut]
if regionInfo['cut']:
sampleCuts.append(regionInfo['cut'])
if self.config.has_option(configSection, 'Datacut'):
sampleCuts.append(self.config.get(configSection, 'Datacut'))
if self.config.has_option('Plot_general','addBlindingCut'):
sampleCuts.append(self.config.has_option('Plot_general', 'addBlindingCut'))
# arbitrary (optional) name for the output tree, used for print-out (the TreeCache object has no idea what it is doing, e.g. dc, plot etc.)
cacheName = 'plot:{region}_{sample}'.format(region=region, sample=sample.name)
# add cache object
tc = TreeCache.TreeCache(
name=cacheName,
sample=sample.name,
cutList=sampleCuts,
inputFolder=self.samplesPath,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
fileList=self.fileList,
branches=keepBranchesPlotFinal,
config=self.config,
debug=True
)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
if not isCached or self.forceRedo:
if isCached:
tc.deleteCachedFiles(chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree({'name': sample.identifier, 'folder': self.samplesPath}, splitFilesChunkSize=self.splitFilesChunkSize, chunkNumber=self.chunkNumber, config=self.config, saveMemory=True)
if not self.sampleTree or not self.sampleTree.tree:
print ("\x1b[31mERROR: creation of sample tree failed!!\x1b[0m")
raise Exception("CreationOfSampleTreeFailed")
# consistency check on the file list at submission time and now
fileListNow = self.sampleTree.getSampleFileNameChunk(self.chunkNumber)
if self.fileList and (sorted(self.fileList) != sorted(fileListNow)):
print ("\x1b[31mERROR: sample files have changed between submission and run of the job!\x1b[0m")
raise Exception("SampleFilesHaveChanged")
treeCaches.append(tc.setSampleTree(self.sampleTree).cache())
else:
print ("INFO: already cached!",tc, "(",tc.hash,")")
if len(treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print ("nothing to do!")
class CacheDatacards(object):
def __init__(self, config, regions, sampleToCache, splitFilesChunks=1, chunkNumber=1, splitFilesChunkSize=-1, forceRedo=False, fileList=None, verbose=False):
self.verbose = verbose
self.config = config
self.regions = regions
self.treeCaches = []
self.sampleTree = None
self.sampleToCache = sampleToCache
self.forceRedo = forceRedo
# settings which part of input files to process
self.splitFilesChunkSize = splitFilesChunkSize
self.splitFilesChunks = splitFilesChunks
self.chunkNumber = chunkNumber
self.fileList = FileList.decompress(fileList) if fileList else None
# initialize Datacard objects
self.dcMakers = [Datacard(config=self.config, region=region) for region in self.regions]
# make a minimum list of samples which is needed to produce all the Datacard regions at the same time
def getAllSamples(self):
samples = []
for dcMaker in self.dcMakers:
for sample in dcMaker.getAllSamples():
if len([x for x in samples if x.name == sample.name]) < 1:
samples.append(sample)
return samples
def prepare(self):
if len(self.dcMakers) > 0:
self.treeCaches = []
self.sampleTree = None
# cuts
allSamples = self.getAllSamples()
subsamples = [x for x in allSamples if x.identifier == self.sampleToCache]
# loop over all datacard regions
for dcMaker in self.dcMakers:
# loop over all subsamples (which come from the same root tree files)
for sample in subsamples:
# combine subcut and systematics cut with logical AND
# systematics cuts are combined with logical OR, such that 1 cache file can be used for all the systematics
isData = (sample.type == 'DATA')
systematicsCuts = sorted(list(set([x['cachecut'] for x in dcMaker.getSystematicsList(isData=isData)])))
sampleCuts = {'AND': [sample.subcut, {'OR': systematicsCuts}]}
if True or self.verbose:
print (json.dumps(sampleCuts, sort_keys=True, indent=8, default=str))
# make list of branches to keep in root file
branchList = BranchList(sample.subcut)
branchList.addCut([x['cachecut'] for x in dcMaker.getSystematicsList()])
branchList.addCut([x['cut'] for x in dcMaker.getSystematicsList()])
branchList.addCut([x['var'] for x in dcMaker.getSystematicsList()])
branchList.addCut([x['weight'] for x in dcMaker.getSystematicsList()])
branchList.addCut(self.config.get('Weights', 'weightF'))
branchList.addCut(eval(self.config.get('Branches', 'keep_branches')))
branchesToKeep = branchList.getListOfBranches()
# arbitrary (optional) name for the output tree, used for print-out (the TreeCache object has no idea what it is doing, e.g. dc, plot etc.)
cacheName = 'dc:{region}_{sample}'.format(region=dcMaker.getRegion(), sample=sample.name)
# add cache object
tc = TreeCache.TreeCache(
name=cacheName,
sample=sample.name,
cutList=sampleCuts,
cutSequenceMode='TREE',
branches=branchesToKeep,
inputFolder=dcMaker.path,
splitFilesChunks=self.splitFilesChunks,
chunkNumber=self.chunkNumber,
splitFilesChunkSize=self.splitFilesChunkSize,
fileList=self.fileList,
config=self.config,
debug=self.verbose
)
# check if this part of the sample is already cached
isCached = tc.partIsCached()
print ("check if sample \x1b[34m{sample}\x1b[0m part {part} is cached:".format(sample=sample.name, part=self.chunkNumber), isCached)
if not isCached or self.forceRedo:
if isCached:
tc.deleteCachedFiles(chunkNumber=self.chunkNumber)
# for the first sample which comes from this files, load the tree
if not self.sampleTree:
self.sampleTree = SampleTree({'name': sample.identifier, 'folder': dcMaker.path}, splitFilesChunkSize=self.splitFilesChunkSize, chunkNumber=self.chunkNumber, config=self.config, saveMemory=True)
if not self.sampleTree or not self.sampleTree.tree:
print ("\x1b[31mERROR: creation of sample tree failed!!\x1b[0m")
raise Exception("CreationOfSampleTreeFailed")
# consistency check on the file list at submission time and now
fileListNow = self.sampleTree.getSampleFileNameChunk(self.chunkNumber)
if self.fileList and (sorted(self.fileList) != sorted(fileListNow)):
print ("\x1b[31mERROR: sample files have changed between submission and run of the job!\x1b[0m")
raise Exception("SampleFilesHaveChanged")
# connect the TreeCache object to the input sampleTree and add it to the list of cached trees
self.treeCaches.append(tc.setSampleTree(self.sampleTree).cache())
else:
print("WARNING: no datacard regions added, nothing to do.")
return self
def run(self):
if len(self.treeCaches) > 0:
# run on the tree
self.sampleTree.process()
else:
print ("nothing to do!")